推薦系統扮演著替使用者篩選需要資訊的角色，近年來的研究顯示使用深度學習的方法，可以更好的去預測使用者喜好的物品，深度學習模型會自己去調整參數的數值，然而這些由模型自己學出來的參數有著不可解釋的問題，這也讓人們很難了解模型背後推薦的機制，難以對模型進行近一步的分析。
為了進一步提升推薦的效能，近年來開始有研究將知識圖納入了推薦之中，其中一類研究只用知識圖來拿到更多的物品特徵，沒有去解決不可解釋的問題，另一類的研究沒有去學習知識圖的表達以及背景知識，直接將知識圖中的路徑作為模型的輸入，在知識圖的資訊有所遺漏時，會無法做出好的推薦。還有一類研究在解釋上面注重在知試圖的關係層面上，因此當有圖中多個不同的屬性與商品或使用者屬於同一個關係時，模型只能解釋在推薦時考慮的關係比重，而不能在屬性層面上做出解釋。
基於上述推薦系統的限制，本研究提出一個結合知識圖以及擁有屬性可解釋性的推薦系統，由知識圖的推論中得到屬性的解釋，因此當模型推薦進行推薦時，可以說明商品被推薦的原因，是因為模型考慮了商品或是使用者本身的哪些特性。此外，為了解決前述屬性遺失的問題，本研究提出的模型除了學習知識圖的表達以及背景知識以外，還會根據目前學習到的知識去預測知識圖中遺失的資訊，並將資訊加入推薦的考量當中。
為了驗證本研究的有效性，我們採用了兩個不同領域的資料集，並分別實驗模型在使用者喜好預測與遺失屬性預測上的效能，由實驗證明，本研究提出模型在不同的資料集以及不同的任務中，預測的結果優於先前的推薦系統的模型(BPR、NeuMF)、知識圖預測模型(TransE、TransH、SimplE)以及其他結合知識圖的推薦模型(KTUP)。

In the era of information explosion, recommendation systems play an important role for each user in many modern Internet services. Studies used ML/DL method to predict user preference in recent years. However, those recommendation systems have the problem of being unexplainable. The problem causes human distrust of the model because humans cannot understand the mechanism within.
For enhancing recommendation performance, recent studies unify the knowledge graph (KG) in recommended systems to get better explanations. Some studies use KG as a new method to get extra features of items, but they don’t solve the unexplainable problem. Some studies use the existing path in KG as the input of the model to predict user preference. These studies didn’t learn knowledge graph representations or have the room for improvement when the knowledge is missing in KG. Another study learns KG representation and unifies KG in the recommendation. However, this method focuses on producing relation explanation on KG. Under this circumstance, when different attributes are connected to the same relation, the model can’t tell which attribute is more important.
In our study, we build the KG-based recommendation system with the attribute explanation. When generating recommendation, our model can show the recommended logic to illustrate which attribute is more important by the inference of KG. In addition, we can predict missing attributes through background knowledge and consider the missing information in recommendation.
To evaluate the overall performance of our model, we design some experiments on separate tasks of item recommendation and attribute prediction. Two different domain datasets are used to show that our method is robust on different domains. The performance of our model is better than the previous recommendation models (BPR, NeuMF), KG models (TransE, TransH, SimplE), and recommendation model unifying KG (KTUP).

Antoine Bordes; Nicolas Usunier; Alberto Garcia-Dur´an;Jason Weston; Oksana Yakhnenko. "Translating Embeddings for Modeling Multi-relational Data". NIPS, 1–9, 2013.

Breese, J. S., Heckerman, D., &Kadie, C. "Empirical Analysis of Predictive Algorithms for Collaborative Filtering". 43–52, 2013.

Cao, Y., Wang, X., He, X., Hu, Z., &Chua, T. S. "Unifying knowledge graph learning and recommendation: Towards a better understanding of user preferences". The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019, 151–161, 2019.

Ding, J., Quan, Y., He, X., Li, Y., &Jin, D. "Reinforced negative sampling for recommendation with exposure data". IJCAI International Joint Conference on Artificial Intelligence, 2019-August, 2230–2236, 2019.

Dong, L., Wei, F., Zhou, M., &Xu, K. "Question answering over freebase with multi-column convolutional neural networks". ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference, 1, 260–269, 2015.

He, R., &McAuley, J. "VBPR: Visual Bayesian personalized ranking from implicit feedback". 30th AAAI Conference on Artificial Intelligence, AAAI 2016, 144–150, 2016.

He, X., Liao, L., Zhang, H., Nie, L., Hu, X., &Chua, T. S. "Neural collaborative filtering". 26th International World Wide Web Conference, WWW 2017, 173–182, 2017.

Hidasi, B., Karatzoglou, A., Baltrunas, L., &Tikk, D. "Session-based recommendations with recurrent neural networks". 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings, 1–10, 2016.

Ji, G., He, S., Xu, L., Liu, K., &Zhao, J. "Knowledge graph embedding via dynamic mapping matrix". ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference, 1, 687–696, 2015.

Kazemi, S. M., &Poole, D. "Simple embedding for link prediction in knowledge graphs". Advances in Neural Information Processing Systems, 2018-Decem(NeurIPS), 4284–4295, 2018.

Kim, D., Park, C., Oh, J., Lee, S., &Yu, H. "Convolutional matrix factorization for document context-aware recommendation". RecSys 2016 - Proceedings of the 10th ACM Conference on Recommender Systems, 233–240, 2016.

Li, J., Ren, P., Chen, Z., Ren, Z., Lian, T., &Ma, J. "Neural attentive session-based recommendation". International Conference on Information and Knowledge Management, Proceedings, Part F1318, 1419–1428, 2017.

Lin, Y., Liu, Z., Sun, M., Liu, Y., &Zhu, X. "Learning entity and relation embeddings for knowledge graph completion". Proceedings of the National Conference on Artificial Intelligence, 3, 2181–2187, 2015.

Meteren, R.Van, &Someren, M.Van. "Using Content-Based Filtering for Recommendation". ECML/MLNET Workshop on Machine Learning and the New Information Age, 47–56, 2000.

Rendle, S., Freudenthaler, C., Gantner, Z., &Schmidt-Thieme, L. "BPR: Bayesian Personalized Ranking from Implicit Feedback". 452–461, 2012.

Socher, R., Chen, D., Manning, C. D., &Ng, A. Y. "Reasoning With Neural Tensor Networks". ArXiv, 2010, 2012.

Trouillon, T., Dance, C. R., Gaussier, E., Welbl, J., Riedel, S., &Bouchard, G. "Knowledge graph completion via complex tensor factorization". Journal of Machine Learning Research, 18, 1–38, 2017.

Wang, H., Zhang, F., Wang, J., Zhao, M., Li, W., Xie, X., &Guo, M. "RippleNet: Propagating user preferences on the knowledge graph for recommender systems". International Conference on Information and Knowledge Management, Proceedings, (1), 417–426, 2018.

Wang, J., Wang, Z., Zhang, D., &Yan, J. "Combining knowledge with deep convolutional neural networks for short text classification". IJCAI International Joint Conference on Artificial Intelligence, 2915–2921, 2017.

Wang, X., He, X., Feng, F., Nie, L., &Chua, T.-S. "TEM: Tree-enhanced Embedding Model for Explainable Recommendation". Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW ’18, (10), 1543–1552, 2018.

Wang, X., Wang, D., Xu, C., He, X., Cao, Y., &Chua, T.-S. "Explainable Reasoning over Knowledge Graphs for Recommendation". Proceedings of the AAAI Conference on Artificial Intelligence, 33, 5329–5336, 2019.

Wang, Z., Zhang, J., Feng, J., &Chen, Z. "Knowledge graph embedding by translating on hyperplanes". Proceedings of the National Conference on Artificial Intelligence, 2, 1112–1119, 2014.

Xian, Y., &Melo, G.De. "Reinforcement Knowledge Graph Reasoning for Explainable Recommendation", 2019.

Xie, R., Liu, Z., Lin, F., &Lin, L. "Does William Shakespeare REALLY write Hamlet? Knowledge representation learning with confidence". 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, 4954–4961, 2018.

Yang, B., Yih, W. tau, He, X., Gao, J., &Deng, L. "Embedding entities and relations for learning and inference in knowledge bases". 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 1–12, 2015.

Yehuda Koren ; Robert Bell ; Chris Volinsky. "Matrix Factorization Techniques for Recommender Systems". IEEE, 199–207, 2009.

Zhang, F., Yuan, N. J., Lian, D., Xie, X., &Ma, W. "Collaborative Knowledge Base Embedding for Recommender Systems". 353–362, 2016.

Zhang, W., Paudel, B., Zhang, W., Bernstein, A., &Chen, H. "Interaction embeddings for prediction and explanation in knowledge graphs". WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining, (February), 96–104, 2019.